WO2019205314A1

WO2019205314A1 - Sleep monitoring method, storage medium and device

Info

Publication number: WO2019205314A1
Application number: PCT/CN2018/096697
Authority: WO
Inventors: 闫正航; 颜宏武
Original assignee: 深圳市友宏科技有限公司
Priority date: 2018-04-23
Filing date: 2018-07-23
Publication date: 2019-10-31

Abstract

Disclosed in the present application are a sleep monitoring method, a storage medium and a device. Said method comprises: acquiring motion data of a human body, and obtaining, at an interval of a preset time period, all the motion data in the current time period; calculating a motion data change amount within the current time period according to all the obtained motion data, and comparing the motion data change amount with a preset change amount threshold; if the motion data change amount is greater than the preset change amount threshold, recording a sleep state of the current time period as a motion state. By comparing the motion data change amount within a preset time period with the preset change amount threshold, the present application can accurately identify whether there is a body motion during sleep. In addition, since the motion data change amount is used as a basis for determination, there is no requirement for the direction of a pressure sensor, thus avoiding the influence of the direction of the pressure sensor on a monitoring result.

Description

Sleep monitoring method, storage medium and device

Technical field

The present application relates to the field of biomedical technology, and in particular, to a sleep monitoring method, a storage medium, and a device.

Background technique

As the pace of life accelerates and the living environment changes, more and more people suffer from sleep disorders. According to a survey of 25,916 patients in 29 countries or regions by the World Health Organization, 27% of people have sleep problems, and about 39% of the total number of people with sleep disorders in China. Suffering from sleep disorders not only seriously affects people's health, but also causes work efficiency and work quality to decline. There is a direct relationship between sleep quality and physical health. The quality of sleep directly affects other diseases such as cardiovascular and cerebrovascular diseases. The incidence of cardiovascular and cerebrovascular diseases is 40% at night. Healthy sleep is critical during the first few months of neonatal development. Therefore, devices have been proposed that allow parents or other caregivers to monitor the sleep of infants, young children, and newborns.

Body movement during sleep is an important technical indicator for monitoring sleep using pressure sensing technology. In the patent 201710055341.2 "A sleepband-based turning-over monitoring device and method", a method for judging whether to turn over based on the maximum value of the physical activity is proposed, which identifies whether or not to turn over based on whether the peak value of the collected voltage signal exceeds a preset threshold. However, the program cannot recognize and judge the body movements that do not reach the extreme value, and thus cannot accurately recognize the movement of the human body during the sleep process.

Application content

In view of the deficiencies of the prior art, the present application is directed to providing a sleep monitoring method, a storage medium, and an apparatus.

In order to solve the above technical problems, the technical solutions adopted in the present application are as follows:

A sleep monitoring method comprising:

Collecting motion data of the human body, and acquiring all motion data in the current time period every preset time period;

Calculating a first change amount of the motion data of the current time period according to the acquired motion data, and comparing the first change amount with the first preset change amount threshold;

If the first change amount is greater than the first preset change amount threshold, the sleep state of the current time period is recorded as a motion state.

The sleep monitoring method, wherein the acquiring the motion data of the human body and acquiring all the motion data in the current time period every preset time period includes:

Sensing the motion data of the human body in real time through a pre-wearing pressure sensor, and storing the sensed motion data, wherein the motion data carries the sensing time;

All motion data corresponding to the current time period is read every preset time period.

The sleep monitoring method, wherein the sensing the motion data of the human body in real time through the pre-wearing pressure sensor, and saving the sensed human motion data specifically includes:

Real-time sensing of human motion information and generating an electrical signal by a preset pressure sensor, and recording the sensing time of the electrical signal;

The motion data of the human body is output according to the electrical signal, and the motion data is stored in association with the sensing time.

The sleep monitoring method, wherein the calculating the first change amount of the current time period according to the acquired all motion data, and comparing the first change amount with the first preset change amount threshold value specifically includes:

Reading a maximum value of the motion data of the acquired motion data and a motion data minimum value, and calculating a first variation amount of the current time period according to the motion data maximum value and the motion data minimum value;

The first amount of change is compared with a preset first preset amount of change threshold.

The sleep monitoring method, wherein, if the first change amount is greater than the first preset change amount threshold, recording the sleep state of the current time period as a motion state specifically includes:

If the first change amount is greater than the first preset change amount threshold, read a time interval corresponding to the current time period;

Recording the motion state corresponding to the time interval as the presence motion motion, and recording the motion intensity of the preset time interval as the first variation amount.

The sleep monitoring method, wherein, if the first change amount is greater than the first preset change amount threshold, recording the sleep state of the current time period as a motion state comprises:

Acquiring the sleep state in the next time period in sequence, and acquiring the first time period in which the sleep state is in the normal sleep state;

Calculating the exercise time in the motion state according to the current time period and the first time period.

The sleep monitoring method, wherein the calculating the exercise time in the exercise state according to the current time period and the first time period specifically includes:

Determining a start time of the motion state according to all motion data included in the current time period, and determining an end time of the motion state according to all motion data included in the first preset time end;

The exercise time in which the exercise state continues is calculated based on the start time and the end time.

The sleep monitoring method, wherein determining the start time of the motion state according to all the motion data included in the current time period, and determining the end time of the motion state according to all the motion data included in the first time period specifically includes:

Comparing all the motion data included in the current time period and all the data included in the first time period with the preset motion data interval, wherein the change amount threshold is a change amount of the preset motion data interval;

Obtaining, in time sequence, first motion data that is not in the preset motion data interval of the current time period, and second motion data that is not in the preset data interval in the first time period to determine a motion state. Start time and end time.

The sleep monitoring method, wherein, if the first change amount is greater than the first preset change amount threshold, the recording the sleep state of the current time period as the exercise state further includes:

Calculating a second change amount of the next time period, and comparing the first change amount and the second change amount with the second preset change amount threshold respectively;

When the first change amount is greater than or equal to the second preset change amount threshold, and the second change amount is less than the second preset change amount threshold, determining that the sleep state of the current time period is in the bed-away state, and recording according to the next time period Get out of bed.

The sleep monitoring method, wherein the method further includes:

When the first change amount is less than the second preset change amount threshold, and the second change amount is greater than or equal to the second preset change amount threshold, determining that the sleep state of the current time period is in the bed state, and recording according to the next time period Bedtime.

The sleep monitoring method, wherein, if the first change amount is greater than the change amount threshold, recording the sleep state of the preset time period as a motion state comprises:

Acquiring the sleep state in the next preset time period in sequence, and acquiring the first time period in which the sleep state is in the going to bed state;

The exercise time in the bed-away state is calculated according to the current time period and the first time period.

The sleep monitoring method, wherein the method further includes:

If the first change amount is smaller than the first preset change amount threshold, compare the first change amount with the second preset change amount threshold;

When the first change amount is greater than the second preset change amount threshold, it is determined that the human body is in a normal sleep state.

The sleep monitoring method, wherein when the first change amount is greater than the second preset change amount threshold, determining that the human body is in a normal sleep state comprises:

Processing the BCG signal to divide it into a number of breathing cycles, wherein the breathing cycle comprises exhalation-inhalation-exhalation;

The exhalation points included in each breathing cycle are respectively offset by a preset offset along the time axis according to a preset rule;

Determining a time period corresponding to each breathing cycle according to the exhaled point after the offset;

The BCG signal is updated according to a time period corresponding to each breathing cycle, and the heart rate is extracted according to the updated BCG signal.

The sleep monitoring method, wherein the collecting a BCG signal and processing the BCG signal to divide it into a plurality of breathing cycles specifically includes:

Collecting a BCG signal and performing low pass filtering on the BCG signal to obtain a respiratory signal;

All extreme points of the respiratory signal are acquired, and the respiratory signal is divided into several breathing cycles according to all the extreme points obtained.

The sleep monitoring method, wherein the obtaining all the extreme points of the respiratory signal and dividing the respiratory signal into a plurality of respiratory periods according to all the extreme points obtained includes:

Obtaining a waveform curve corresponding to the waveform signal, and determining all maximum value points of the waveform signal according to the waveform curve;

The breathing signal is divided into a plurality of breathing cycles according to all the extracted maximum points, wherein the interval formed by the two adjacent maxima is one breathing cycle.

The sleep monitoring method, wherein the exchanging exhalation points of each breathing cycle according to a preset rule along a time axis by a preset offset specifically includes:

For each breathing cycle, the exhalation points included in the breathing cycle are sorted in chronological order;

According to the sorting order, the first exhalation point is shifted back by a preset offset along the time axis, and the second exhalation point is forwardly offset by a preset offset along the time axis.

The sleep monitoring method, wherein the sorting the exhalation points included in the breathing cycle in chronological order for each respiratory cycle comprises:

Obtaining, according to the sorting order, a first moment corresponding to the first exhalation point and a second moment corresponding to the second exhalation point;

And calculating the preset offset according to the first time and the second time, wherein the preset offset=(second time−first time)/10.

The sleep monitoring method, wherein the updating the BCG signal according to a time period corresponding to each breathing cycle, and extracting the heart rate according to the updated BCG signal specifically includes:

Obtaining a first BCG signal corresponding to each time segment, and splicing each first BCG signal in time sequence to form an updated BCG signal;

The heart rate is extracted based on the updated BCG signal.

A computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement a sleep monitoring method as described above The steps in .

A sleep monitoring device includes: a pressure sensor, a processor, a memory, and a communication bus; and the memory stores a computer readable program executable by the processor;

The communication bus implements connection communication between the processor and the memory;

The pressure sensor realizes acquisition of motion data, and transmits the collected motion data to a processor;

The processor of the present invention, when the computer readable program is executed, implements the steps of the sleep monitoring method of any of claims 1-18.

Advantageous Effects: Compared with the prior art, the present application provides a sleep monitoring method, a storage medium, and a device, the method comprising: collecting motion data of a human body, and acquiring all motions in a current time period every preset time period. Data; calculating, according to all the acquired motion data, the motion data change amount of the current time period, and comparing the motion data change amount with a preset change amount threshold; if the motion data change amount is greater than the preset The change amount threshold records the sleep state of the current time period as a motion state. The present application can accurately identify the presence or absence of body motion during sleep by comparing the amount of change in motion data within a preset time period with a preset threshold of change. At the same time, since the change of the motion data is used as the judgment basis, the direction of the pressure sensor is not required, and the influence of the direction of the pressure sensor on the monitoring result can be avoided.

DRAWINGS

FIG. 1 is a flowchart of Embodiment 1 of a sleep monitoring method provided by the present application.

FIG. 2 is a diagram showing changes in motion data of a normal sleep state in the first embodiment of the sleep monitoring method provided by the present application.

FIG. 3 is a diagram showing motion data changes of a sleep process in which body motion is started in the first embodiment of the sleep monitoring method provided by the present application.

FIG. 4 is a diagram showing changes in body motion end motion data during sleep in the first embodiment of the sleep monitoring method provided by the present application.

FIG. 5 is a diagram showing changes in exercise data of going to bed, getting out of bed, and going out of bed in the third embodiment of the sleep monitoring method provided by the present application.

FIG. 6 is a waveform diagram of a BCG signal in Embodiment 4 of the sleep monitoring method provided by the present application.

FIG. 7 is a waveform diagram of a respiratory signal in Embodiment 4 of the sleep monitoring method provided by the present application.

FIG. 8 is a waveform diagram of exhalation point offset in a BCG signal in Embodiment 4 of the sleep monitoring method provided by the present application.

FIG. 9 is a schematic structural diagram of an embodiment of a sleep monitoring method apparatus provided by the present application.

detailed description

The present application provides a sleep monitoring method, a storage medium, and an apparatus. The objects, technical solutions, and effects of the present application will become more apparent and clear, and the present application will be further described in detail below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The singular forms "a", "an", "the" It is to be understood that the phrase "comprise" or "an" Integers, steps, operations, components, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element. Further, "connected" or "coupled" as used herein may include either a wireless connection or a wireless coupling. The phrase "and/or" used herein includes all or any one and all combinations of one or more of the associated listed.

Those skilled in the art will appreciate that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. It should also be understood that terms such as those defined in a general dictionary should be understood to have meaning consistent with the meaning in the context of the prior art, and will not be idealized or excessive unless specifically defined as here. The formal meaning is explained.

The contents of the application will be further described below with reference to the accompanying drawings.

Embodiment 1

The sleep monitoring method provided in this embodiment is as shown in FIG. 1-4, and the method includes:

S10: Collect motion data of the human body, and acquire all motion data in the current time period every preset time period.

Specifically, the preset time is preset to control a frequency of reading the collected motion data, where the current time period refers to a preset time period before the current reading time, that is, the latest one. The preset time period is the current time period. All the motion data of the current time period may be correlated according to the sampling frequency of the motion data, and the data amount of all the motion data included in the current time period may be determined according to the duration of the preset time period and the sampling frequency. For example, the preset time period Ts is 1 second, the acquired motion data has a resolution Ns of 16 bits, the sampling frequency Fs is 250 Hz, and the collected motion data Ds has a size range of 0-2^Ns (0-65535 bits).

Meanwhile, in the embodiment, the exercise data is data of lung and limb activity of the human body during the sleep process. The motion data can be sensed and collected by a pressure sensor worn by the human body. Correspondingly, the acquiring the motion data of the human body and acquiring all the motion data in the current time period every preset time period includes:

S11. The motion data of the human body is sensed in real time by a pressure sensor worn in advance, and the sensed motion data is saved, wherein the motion data carries the sensing time;

S12. Read all motion data corresponding to the current time period every preset time period.

Specifically, the pressure sensor is pre-weared by a human body, wherein the human body can wear the pressure sensor in the form of a wearing device (eg, a sleep belt, etc.), or the pressure monitoring device can be worn in the form of a sleep monitoring bed and a sleep monitoring pillow. . That is to say, the pressure sensor only needs to be able to sense the movement of the human body, and the form of the human body wearing the sensor is not limited herein. In addition, after sensing the motion of the human body, the pressure sensor generates an electrical signal according to the motion information of the human body, and determines the motion data of the human body through the electrical signal. Correspondingly, the sensing the motion data of the human body in real time through the pre-wearing pressure sensor, and saving the sensed human motion data specifically includes:

S111: sensing body motion information and generating an electrical signal in real time through a preset pressure sensor, and recording an induction time of the electrical signal;

S112. Output motion data of the human body according to the electrical signal, and store the motion data in association with the sensing time.

In this embodiment, after the pressure sensor senses the motion information of the human body and generates an electrical signal, the electrical signal is limited to suppress the power frequency interference of the electrical signal, and the signal after the limited wave is amplified, and filtered. In addition to the baseline drift and high frequency noise signals; the filtered electrical signals are then converted to digital signals, and finally the digital signals are processed to obtain motion data corresponding to the electrical signals, which can improve the accuracy of the motion data, thereby improving motion The accuracy of the status detection. At the same time, after obtaining the motion data, the application does not need to process the motion data, which simplifies the operation process and improves the efficiency of the motion state detection. At the same time, the requirements for hardware devices are reduced, and the applicability of the method is expanded.

In addition, in order to facilitate the recording of the time of the human body movement, when the electrical signal is collected, the sensing time can be acquired, and the sensing time is associated with the electrical signal, so that each motion data is configured with a corresponding sensing time, thereby The motion data and the sensing time can regularly and quantitatively monitor the human motion, which improves the comprehensiveness of the motion state monitoring. In this embodiment, the sensing time may be obtained by reading the current time of the system of the hardware device that receives the electrical signal, or may be determined by the pressure sensor when sensing the motion signal of the human body. Certainly, the sensing time may also be determined according to the sampling frequency and the current time period in which the electrical signal is located, which may be: firstly acquiring all the starting time, the preset time, and the reading current time of starting the human body motion data acquisition. The number of times the motion data is read may be determined according to the starting time, the preset time, and the number of readings, and the time interval in which the current time period is located may be determined, and the sensing time corresponding to the current electrical signal may be determined according to the sampling frequency. That is to say, when all the motion data included in the current time period is acquired every preset time interval, the number of readings may also be recorded, so as to determine the sensing time corresponding to the current electrical signal according to the number of readings.

At the same time, in the embodiment, the sleep detecting device may be turned on before the motion data of the human body is collected, and then the pressure sensor included in the sleep detecting device is turned on to detect the body motion data, for example, a control button (such as a mechanical button) set by the sleep detecting device. The sleep detection device is turned on by means of remote sensing or the like. In addition, the sleep detecting device can also adopt an automatic starting mode, that is, when the pressure sensor detects the pressure, the sleep detecting device is automatically turned on and the human body motion data is collected. Of course, in the actual application, after acquiring the motion data of the human body, the preset time period may also include a sleep state detection process before acquiring all the motion data in the current time period, and the sleep state detection process is used for detecting Whether the human body is sleeping. The sleep detection process may be specifically: reading human motion data in real time, and comparing the motion data with a preset motion data interval, and determining, when the motion data number is in a preset motion data interval and continuing for a predetermined time. The human body is in a sleep state. All motion data in the current time period is acquired every predetermined time period after determining that the human body enters a sleep state. In addition, the sleep detection process may also adopt other methods, for example, determining whether the human body sleeps or not according to the human brain electrical signal, which will not be described here.

S20. Calculate a motion data change amount of the current time period according to the acquired motion data, and compare the motion data change amount with a preset change amount threshold.

Specifically, the preset change amount threshold is preset, which may be a difference between an upper limit value and a lower limit value of the preset motion data interval. For example, suppose the preset data interval is [DND-DNU], wherein the preset data interval may be an empirical value obtained by a large number of experimental statistical analysis, DND is 22768, DNU is 42768, then the preset variation threshold = 42768 -22768. The motion data change amount is a difference between the maximum value of the motion data and the motion data minimum value in the current time period. Correspondingly, the calculating the motion data change amount of the current time period according to the acquired motion data, and comparing the motion data change amount with the preset change amount threshold value specifically includes:

S21: reading a motion data maximum value of the acquired motion data and a motion data minimum value, and calculating a motion data change amount of the current time period according to the motion data maximum value and the motion data minimum value;

S22. Compare the motion data change amount with a preset preset change amount threshold.

Specifically, after reading all the motion data included in the current time period, the motion data maximum value and the motion data minimum value are extracted in all the motion data, and the motion is obtained by calculating the difference between the motion data maximum value and the motion data minimum value. The amount of data change BM _Str . The motion data change amount is compared with a preset change amount threshold BM _Th , where BM _Th =DNU-DND.

S30. If the motion data change amount is greater than the preset change amount threshold, record the sleep state of the current time period as a motion state.

Specifically, the motion data change amount is greater than the preset change amount threshold value, indicating that there is a body motion action in the current time period, and the body running strength is recorded as BM _Str . In addition, the corresponding time interval is determined according to the current time period, and the time interval is stored corresponding to the motion state and the exercise intensity, so that it is convenient to quickly determine the time and exercise intensity of the body to generate the body motion. Correspondingly, if the motion data change amount is greater than the preset change amount threshold, recording the sleep state of the current time period as the motion state specifically includes: if the motion data change amount is greater than the preset The change amount threshold is used to read the time interval corresponding to the current time period; record the motion state corresponding to the time interval as the presence of the motion action, and record the exercise intensity of the preset time interval as the motion data change the amount. In addition, if the motion data change amount is less than or equal to the change amount threshold, it is determined that the human body is in a normal sleep state, and all human motion data of the next time period is continuously read.

In an embodiment of the present application, if the motion data change amount is greater than the preset change amount threshold, recording the sleep state of the current time period as the motion state includes:

S40: sequentially acquire a sleep state in a next time period, and obtain a first time period in which the sleep state is in a normal sleep state;

S50. Calculate a motion time in a motion state according to the current time period and the first time period.

Specifically, the current time period is recorded as the starting time of the body motion, and the body motion intensity is BM _Str , and then the motion state of each preset time period is continuously acquired until the first time period in the normal sleep state is acquired, that is, the first time period The motion data change amount BM _Str <=BM _{Th in} a period of time records the end of the body motion for the first time period, so that the duration of the body motion can be determined according to the current time period and the first time period. Of course, in the first time period in which the normal sleep state is acquired, only the current body motion end is indicated, but the motion data of each preset time period is continuously read to detect the next body motion, and so on until the human body motion. The data collection is over.

Exemplarily, the calculating the exercise time in the motion state according to the current time period and the first time period specifically includes:

S51: Determine a start time of the motion state according to all motion data included in the current time period, and determine an end time of the motion state according to all motion data included in the first preset time end;

S52. Calculate a duration of motion of the motion state according to the start time and the end time.

Further, the determining the start time of the motion state according to all the motion data included in the current time period, and determining the end time of the motion state according to all the motion data included in the first time period specifically includes:

Embodiment 2

This embodiment provides a sleep monitoring method, including:

H10: Collect motion data of the human body, and acquire all motion data in the current time period every preset time period.

H20: respectively calculate a first change amount of the current time period and a second change amount of the next time period, and compare the first change amount and the second change amount with the preset change amount threshold respectively.

H30. When the first change amount is greater than or equal to the preset change amount threshold, and the second change amount is less than the preset change amount threshold, determine that the sleep state of the current time period is in a bed-away state, and record the next time period to get out of bed. time.

In this embodiment, the process of the motion data collection in the step H10 is the same as the process in the step S10 in the first embodiment, and details are not described herein. The difference between this embodiment and the first embodiment is that the processing procedure of the used motion data is different, and the pressure sensor is arranged in different manners. In the embodiment, the pressure sensor is used for sleeping the bed or sleeping to detect the pillow. Formally, the pressure sensor does not detect human motion information when the human body leaves the bed. Specifically, in the step S20, the first change amount of the current time period and the second change amount of the next time period are respectively calculated, and the values of the preset change amount threshold are different. In this embodiment, The preset change amount threshold is a difference value of the preset data interval [NSD-NSU], wherein the preset data interval may be an empirical value obtained by a large number of experimental statistical analysis. For example, if the NSD is 32268 and the NSU is 33268, then the preset change amount threshold OFF _Th may be NSU-NSD. The first change amount is a difference between a maximum value of the motion data and a minimum value of the motion data in the current time period, and the second change amount is a difference between the maximum value of the motion data and the minimum value of the motion data in the next time period. Correspondingly, the calculating the first change amount of the current time period and the second change amount of the next time period respectively, and comparing the first change amount and the second change amount with the preset change amount threshold respectively, respectively:

H21, respectively reading the current time period and the maximum value of the motion data of the next time period and the minimum value of the motion data;

H22. Calculate a first change amount in the current time period according to a maximum value of the motion data of the current time and a minimum value of the motion data;

H23. Calculate a first change amount in the current time period according to a maximum value of the motion data of the previous time and a minimum value of the motion data;

H24. Compare the first change amount and the second change amount with a preset preset change amount threshold.

Specifically, after all the motion data included in the current time period is read, the maximum value of the motion data and the minimum value of the motion data are extracted in all the motion data, and the difference between the maximum value of the motion data and the minimum value of the motion data is obtained. A variation BM _Str1 . The first change amount is compared with a preset change amount threshold OFF _Th , where OFF _Th = NSU - NSD. Similarly, the second change amount BM _{Str2 is} obtained based on the detection of the maximum value of the motion data and the minimum value of the motion data of all the motion data acquired in the next time period, and the second change amount is compared with the preset change amount threshold OFF _Th .

Further, in the step H30, the first change amount is smaller than the preset change amount threshold, indicating that the current time period is in the bed state, and the second change amount is greater than the preset change amount threshold, indicating that the next time period is The state of leaving the bed, thereby judging that the user is in the bed-away state, and the next time is the bed-out period. Thereby, the bedtime can be determined according to the next time period, and the bedtime can be stored, so that it is convenient to quickly determine the bedtime of the human body. In addition, when the first change amount is less than the preset change amount threshold, and the second change amount is greater than or equal to the preset change amount threshold, it is determined that the sleep state of the current time period is in the bed state, and the user is determined to go to the bed according to the next time period. time. For example, the start time of the next time period is recorded as the bedtime, or the end time of the next time period is recorded as the bedtime or the like.

H40, sequentially acquiring a sleep state in a next preset time period, and acquiring a first time period in which the sleep state is in a going to bed state;

H50. Calculate the exercise time in the state of leaving the bed according to the current time period and the first time period.

Specifically, the next time period is recorded as the starting time of the bed-away state, and then the motion state of each preset time period is continuously acquired until the first time period in the normal sleep state, that is, the first time period, is acquired. The motion data change amount BM _Str >=OFF _Th , the first time period is recorded as the end time of the bed release state, that is, the first time period is the body bedtime, so according to the next time period and the first time period The duration of the bed-away state can be determined. Of course, after acquiring the first period of time in the state of going to bed, the motion data of each preset time period is continuously read to detect the next state of leaving the bed, and so on until the end of the human body motion data collection.

H51. Determine a start time of the motion state according to all motion data included in the current time period, and determine an end time of the motion state according to all motion data included in the first preset time end;

H52. Calculate a duration of motion of the motion state according to the start time and the end time.

Further, determining the start time of the motion state according to all the motion data included in the current time period, and determining the end time of the bed-out state according to all the motion data included in the first time period specifically includes:

Obtaining, in chronological order, first motion data that is not in the preset motion data interval of the current time period, and second motion data that is not in the preset data interval in the first time period, to determine the state of leaving the bed. The start time and the end time.

In addition, in order to explain in detail the process of determining the exercise time of the bed-away state, further explanation will be given below with reference to FIG. 5. As shown in FIG. 5, during the period from 0 to T1, the variable amount is less than the preset change amount threshold, and the human body is in the bed-away state; at time T2, since BM _Str (T2)>=OFF _Th and T1 is the bed-out State, so T2 is the time of going to bed; between T2 and T3, BM _Str is greater than OFF _Th , the human body is in bed state, at time T4, because BM _Str (T4) < OFF _Th , T4 moment is the human body In the state of leaving the bed, the time point T4 is judged as the time of getting out of bed, so that it is possible to obtain the bed time from the time T2 to the time T4.

Embodiment 3

This embodiment provides a sleep state detecting method, including:

M10, collecting motion data of the human body, and acquiring all motion data of all time periods of the motion data in the current time period every preset time period;

M20: Calculate a first change amount of the current time period according to all acquired motion data, and compare the first change amount with a first change amount threshold;

M30. When the first change amount is greater than the first change amount threshold, record the sleep state of the current time period as a motion state, and acquire a second change amount of the next time period;

M40. Compare the second change amount with the second change amount threshold and the first change amount threshold respectively;

M50. If the second change amount is less than the second change amount threshold, determine that the sleep state of the next time is in a bed-away state, and record the bed-out time according to the next time period;

M60. If the second change amount is greater than the second change amount threshold and less than the first change amount threshold, determine that the human body is in a normal sleep state.

Further, the sleep state detecting method further includes:

M70. If the first change amount is less than the first change amount threshold, compare the first change amount with the second change amount threshold;

M80. If the first change amount is greater than the second change amount threshold, determine that the human body is in a normal sleep state;

M90. If the first change amount is less than the second change amount threshold, determine that the human body is in a bed-away state.

In this embodiment, the first change amount threshold is the change amount threshold in the first embodiment, and the second change amount threshold is the change amount threshold in the second embodiment, which is not described herein. In addition, and the pressure sensor does not sense human motion information when the human body leaves the bed.

Embodiment 4

This embodiment provides a sleep monitoring method, including:

L10, collecting motion data of the human body, and acquiring all motion data of all time periods of the motion data in the current time period every preset time period;

L20: Calculate a first change amount of the current time period according to all acquired motion data, and compare the first change amount with a first change amount threshold;

L30. When the first change amount is greater than the first change amount threshold, record the sleep state of the current time period as a motion state, and acquire a second change amount of the next time period;

L40. Compare the second change amount with the second change amount threshold and the first change amount threshold respectively;

L50. If the second change amount is less than the second change amount threshold, determine that the sleep state of the next time is in a bed-away state, and record the bed-out time according to the next time period;

L60. If the second change amount is greater than the second change amount threshold and less than the first change amount threshold, determine that the human body is in a normal sleep state.

Further, the sleep monitoring method further includes:

Further, if the first change amount is greater than the second change amount threshold, determining that the human body is in a normal sleep state specifically includes:

M81, processing the BCG signal to divide it into several breathing cycles, wherein the breathing cycle includes exhalation-inhalation-exhalation;

M82, respectively, exchanging exhalation points included in each breathing cycle according to a preset rule along a time axis by a preset offset;

M83, determining a time period corresponding to each breathing cycle according to the exhaled point after the offset;

M84: Update the BCG signal according to a time period corresponding to each breathing cycle, and extract a heart rate according to the updated BCG signal.

Specifically, in the step M81, the BCG signal (Ballistocardiography) can be acquired by a sensor, and the sensor can be directly in contact with the human body, and can be disposed in a stool, a mattress, a pillow, and the like. . Of course, the subject acquires the BCG signal through the sensor after setting the sensor item and is in a static state, and the BCG signal can be as shown in FIG. 6. This can avoid large motions that have motion artifacts in the BCG signal, which affects heart rate analysis and the accuracy of the extraction.

In addition, processing the BCG signal may be processing the BCG signal in a preset time period, that is, when collecting the BCG signal, the BCG signal corresponding to the current time period may be acquired every preset time interval, and the current BCG signal is obtained. The BCG signal corresponding to the time period is processed to divide the BCG signal corresponding to the current time period into several breathing cycles. Correspondingly, the BCG signal is collected, and the BCG signal is processed to divide it into a plurality of breathing cycles, specifically: collecting a BCG signal, and acquiring a BCG signal corresponding to the current time period every preset time interval.

The preset time is preset, which may obtain the duration of the human breathing cycle according to an experiment, and determine the preset time according to the duration of the breathing cycle, so that the BCG signal corresponding to the preset time includes only one breathing cycle. This can avoid the treatment of repeated breathing points and improve the efficiency of heart rate extraction. For example, in a preferred embodiment of the present application, the human respiratory frequency ranges from 5 to 30 beats per minute, and the range of the preset time can be determined according to the respiratory frequency range, that is, the range of the preset time can be Correspondingly, the preset time may preferably be 7 seconds or the like.

In the embodiment, the processing of the BCG signal refers to low-pass filtering the BCG signal to obtain a corresponding breathing signal, and determining a breathing cycle according to the breathing signal. Correspondingly, the collecting the BCG signal and processing the BCG signal to divide it into several breathing cycles specifically includes:

Specifically, the BCG signal includes a heart rate signal and a respiratory signal, and the heart rate signal and the respiratory signal can be separated by a filter. For example, low pass filtering below 1 Hz produces a respiratory component that can be extracted by filtering through a high pass filter (eg, a 2-band Butterworth filter with a ring frequency of 0.8 to 1.2). In this embodiment, the BCG signal needs to be filtered to obtain a respiratory component thereof, that is, a respiratory signal corresponding to the BCG signal is obtained, so that the BCG signal is low-pass filtered to obtain the BCG signal. Corresponding respiratory signal. Wherein, the low pass filter may adopt a band pass filter, and the DC signal and the high frequency signal are removed by the band pass filter to obtain a breath corresponding to the BCG signal.

In addition, the extreme point may be determined according to a breathing curve corresponding to the breathing signal, so that after the breathing signal is acquired, a breathing curve corresponding to the breathing signal is determined, and the breathing curve determined by the person determines each corresponding to the breathing signal. Extreme point, which determines the respiratory cycle it contains based on each extreme point. Correspondingly, the obtaining all the extreme points of the respiratory signal and dividing the respiratory signal into a plurality of breathing cycles according to all the obtained extreme points specifically includes:

Specifically, the breathing curve corresponding to the breathing signal is a sinusoid, and all peaks of the sinusoid are selected to obtain all the maximum points of the breathing signal. For example, as shown in FIG. 7, the waveform of the breathing signal is sinusoidal, so that the extreme points included in the breathing signal can be determined according to the waveform of the breathing signal, for example, T1, TE, and T2 are the breathing. The extreme point of the breathing curve corresponding to the signal. Wherein T1 and T2 are maximum points of the breathing curve, and TE is a minimum point of the breathing curve. In addition, since the gradient of the data change at the TE is smaller than the gradient at the two positions T1 and T2, the TE point is determined to be the exhalation point, and the T1 point and the T2 point are the inhalation points, so that the T1-TE- T2 constitutes an exhalation cycle, the time difference of T1 to T2 is one breathing cycle, and the respiratory frequency of the period T1 to T2 can be calculated according to the time difference. In addition, when the breathing signal includes multiple breathing cycles, all breathing periods included in the breathing signal may be determined according to all maximum values included in the breathing curve corresponding to the breathing signal, and the breathing signal is to be according to the breathing cycle. It is divided into several segments, wherein each breathing signal corresponds to one breathing cycle, that is, each breathing signal includes two inhalation points and one exhalation point. That is to say, after all the maximum values contained in the breathing curve corresponding to the respiratory signal are acquired, the time period between each adjacent two maximum value points corresponds to one breathing cycle. In practical applications, the maximum value of the respiratory signal can be obtained by other methods, such as an modal algorithm.

Further, in the step M82, the preset rule is preset, and the location of the exhalation point is adjusted according to the preset rule to filter the real breathing point from the BCG signal. The preset rule may be that the exhalation point at the front end in time sequence is shifted backward, and the exhalation point at the rear end is shifted forward so that the adjusted breathing cycle does not include the real exhalation point.

Exemplarily, the exhaling points of each breathing cycle are respectively offset along the time axis by a preset offset according to a preset rule, and specifically include:

Specifically, the preset offset may be preset, for example, 0.5 s or the like, which may be determined according to an exhalation point corresponding to the breathing cycle. In this embodiment, the preset offset is preferably determined according to an exhalation point corresponding to the breathing cycle, such that the preset offset may be different for a human body of different respiratory frequencies, such that the preset offset The quantity is more versatile. In addition, the preset offset may be calculated after the exhalation point is acquired, and the exhalation points included in the respiratory cycle are sorted in chronological order, so that the preset offset may be simplified. The calculation process of the quantity. Correspondingly, for each breathing cycle, sorting the exhalation points included in the breathing cycle in chronological order includes:

Specifically, the first time is a time point at which the first exhalation point is collected, and the second time is a time point at which the second exhalation point is collected.

Further, in the step M83, the time period in the step S is a time interval of a time point corresponding to the exhaled point after the offset. For example, as shown in FIG. 8, the exhalation points before the offset are respectively T1 and T2, the preset offset is ΔT, and the exhaled points after the offset are T1' and T2', respectively. The time period = T2'-T1'.

Further, in the step M84, updating the BCG signal according to the time corresponding to each breathing cycle means that the BCG signals corresponding to the respective time segments are spliced to form a new BCG signal, wherein the new BCG signal The BCG signal removes the exhalation point. The updated BCG signal is high-pass filtered to obtain a heart rate signal, and the heart rate is extracted based on the heart rate signal. Correspondingly, the updating the BCG signal according to the time period corresponding to each breathing cycle, and extracting the heart rate according to the updated BCG signal specifically includes:

The heart rate is extracted based on the updated BCG signal.

Specifically, the chronological splicing refers to sorting each first CBG signal in chronological order, and connecting signals corresponding to two adjacent time segments to obtain an updated BCG signal, in the updated BCG. The signal is high pass filtered to extract the heart rate. That is, the extracting the heart rate according to the updated BCG signal specifically includes: performing high-pass filtering on the updated BCG signal to obtain a heart rate signal; extracting peak points of the heart rate signal, and determining a heart rate according to the extracted peak point. . Of course, in practical applications, each first BCG signal can be directly high-pass filtered, and the heart rate corresponding to the first BCG signal is determined according to the high-pass filtered first BCG signal, so that a continuous heart rate value can be obtained, thereby avoiding The splicing process of the first BCG signal improves the efficiency of heart rate extraction.

Embodiment 5

The embodiment provides a sleep monitoring method. The sleep monitoring method can be used for a human body sleep monitoring process. During the human body sleep monitoring process, the BCG signal of the human body can be collected by a pressure sensor, and then the BCG signal is analyzed to Determining a state in which the human body is located according to the BCG signal, the state including a bed release state, a bed state, a motion state, and a normal sleep state; and when the human body is in a normal sleep state, obtaining a normal sleep according to the BCG signal The heart rate of the state, in order to monitor the state of the human body according to the heart rate. Correspondingly, the sleep monitoring method specifically includes:

H10: Collect a BCG signal, acquire a BCG signal corresponding to the current time period every preset time interval, and convert the BCG signal into human motion data.

H20: Calculate a first change amount of the motion data of the current time period according to the acquired motion data, and compare the first change amount with a first preset change amount threshold;

H30. If the first change amount is smaller than the first preset change amount threshold, process the BCG signal to divide it into a plurality of breathing cycles, wherein the breathing cycle includes exhalation-inhalation- expiration;

H40, respectively, exchanging exhalation points included in each breathing cycle according to a preset rule along a time axis by a preset offset;

H50, determining a time period corresponding to each breathing cycle according to the exhaled point after the offset;

H60, updating the BCG signal according to a time period corresponding to each breathing cycle, and extracting a heart rate according to the updated BCG signal

Specifically, the processing procedure of the steps H30-H60 of the embodiment is the same as that of the third embodiment, and the steps H10 and H20 are mainly described in detail.

In the step H10, the preset time is preset for controlling the frequency of reading the collected motion data, wherein the current time period refers to a preset time period before the current reading time. , that is, the latest preset time period is the current time period. All the motion data of the current time period may be correlated according to the sampling frequency of the motion data, and the data amount of all the motion data included in the current time period may be determined according to the duration of the preset time period and the sampling frequency. For example, the preset time period Ts is 1 second, the acquired motion data has a resolution Ns of 16 bits, the sampling frequency Fs is 250 Hz, and the collected motion data Ds has a size range of 0-2^Ns (0-65535 bits).

At the same time, in the embodiment, the motion data is motion data generated by the human body during sleep, and the motion data can be sensed and collected by a pressure sensor worn by the human body. Correspondingly, the acquiring the motion data of the human body and acquiring all the motion data in the current time period every preset time period includes:

H11. The motion data of the human body is sensed in real time through a pre-wearing pressure sensor, and the sensed motion data is saved, wherein the motion data carries the sensing time;

H12: Read all motion data corresponding to the current time period every preset time period.

H111. The human body motion information is sensed in real time by a preset pressure sensor, and an electrical signal is generated, and the sensing time of the electrical signal is recorded;

H112. Output motion data of the human body according to the electrical signal, and store the motion data in association with the sensing time.

At the same time, in the embodiment, the sleep detecting device may be turned on before the motion data of the human body is collected, and then the pressure sensor included in the sleep detecting device is turned on to detect the body motion data, for example, a control button (such as a mechanical button) set by the sleep detecting device. The sleep detection device is turned on by means of remote sensing or the like. In addition, the sleep detecting device may also adopt an automatic starting mode, that is, when the pressure sensor detects the pressure, the sleep detecting device is automatically turned on and the human body motion data is collected. Of course, in the actual application, after acquiring the motion data of the human body, the preset time period may also include a sleep state detection process before acquiring all the motion data in the current time period, and the sleep state detection process is used for detecting Whether the human body is sleeping. The sleep detection process may be specifically: reading human motion data in real time, and comparing the motion data with a preset motion data interval, and determining, when the motion data number is in a preset motion data interval and continuing for a predetermined time. The human body is in a sleep state. All motion data in the current time period is acquired every predetermined time period after determining that the human body enters a sleep state. In addition, the sleep detection process may also adopt other methods, for example, determining whether the human body sleeps or not according to the human brain electrical signal, which will not be described here.

Further, in the H20, specifically, the preset change amount threshold is preset, which may be a difference between an upper limit value and a lower limit value of the preset motion data interval. For example, suppose the preset data interval is [DND-DNU], wherein the preset data interval may be an empirical value obtained by a large number of experimental statistical analysis, DND is 22768, DNU is 42768, then the preset variation threshold = 42768 -22768. The first amount of change is a difference between a maximum value of the motion data and a minimum value of the motion data in the current time period. Correspondingly, the calculating the first change amount of the current time period according to the acquired all the motion data, and comparing the first change amount with the preset change amount threshold value specifically includes:

H21, reading a maximum value of the motion data of the acquired motion data and a motion data minimum value, and calculating a first variation amount of the current time period according to the motion data maximum value and the motion data minimum value;

H22. Compare the first change amount with a preset preset change amount threshold.

Specifically, after all the motion data included in the current time period is read, the maximum value of the motion data and the minimum value of the motion data are extracted in all the motion data, and the difference between the maximum value of the motion data and the minimum value of the motion data is obtained. A variation of BM _Str . The first amount of change is compared to a preset amount of change threshold BM _Th , where BM _Th =DNU-DND.

Based on the above sleep monitoring method, the present application also provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors To achieve the steps in the sleep monitoring method described in the above embodiments.

Based on the sleep monitoring method described above, the present application further provides a BCG heart rate extraction device, as shown in FIG. 9, which includes at least one processor 20; a pressure sensor 21; and a memory 22, which may also include communication. Interface (Communications Interface) 23 and bus 24. Among them, the processor 20, the pressure sensor 21, the memory 22, and the communication interface 23 can complete communication with each other through the bus 24. The pressure sensor 21 is arranged to sense human body operating information and generate an electrical signal. The communication interface 23 can transmit information. Processor 20 may invoke logic instructions in memory 22 to perform the methods in the above-described embodiments.

In addition, the logic instructions in the memory 22 described above may be implemented in the form of software functional units and sold or used as separate products, and may be stored in a computer readable storage medium.

The memory 22 is a computer readable storage medium, and can be configured to store a software program, a computer executable program, a program instruction or a module corresponding to the method in the embodiment of the present disclosure. The processor 30 performs the functional application and data processing by executing software programs, instructions or modules stored in the memory 22, i.e., implements the methods in the above embodiments.

The memory 22 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the terminal device, and the like. Further, the memory 22 may include a high speed random access memory, and may also include a nonvolatile memory. For example, a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., may also be used to store a program code. State storage medium.

In addition, the above-described storage medium and the specific processes loaded and executed by the plurality of instruction processors in the mobile terminal have been described in detail in the above methods, and will not be further described herein.

Finally, it should be noted that the above embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still The technical solutions described in the foregoing embodiments are modified, or the equivalents of the technical features are replaced by the equivalents. The modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

A sleep monitoring method, characterized in that it comprises:

Collecting motion data of the human body, and acquiring all motion data in the current time period every preset time period;

Calculating a first change amount of the motion data of the current time period according to the acquired motion data, and comparing the first change amount with the first preset change amount threshold;

If the first change amount is greater than the first preset change amount threshold, the sleep state of the current time period is recorded as a motion state.
The sleep monitoring method according to claim 1, wherein the acquiring the motion data of the human body and acquiring all the motion data in the current time period every predetermined time period comprises:

Sensing the motion data of the human body in real time through a pre-wearing pressure sensor, and storing the sensed motion data, wherein the motion data carries the sensing time;

All motion data corresponding to the current time period is read every preset time period.
The sleep monitoring method according to claim 2, wherein the sensing the motion data of the human body in real time through the pre-wearing pressure sensor and storing the sensed human motion data specifically includes:

Real-time sensing of human motion information and generating an electrical signal by a preset pressure sensor, and recording the sensing time of the electrical signal;

The motion data of the human body is output according to the electrical signal, and the motion data is stored in association with the sensing time.
The sleep monitoring method according to claim 1, wherein the calculating the first change amount of the current time period according to the acquired motion data, and the first change amount and the first preset change amount Comparison of thresholds specifically includes:

Reading a maximum value of the motion data of the acquired motion data and a motion data minimum value, and calculating a first variation amount of the current time period according to the motion data maximum value and the motion data minimum value;

The first amount of change is compared with a preset first preset amount of change threshold.
The sleep monitoring method according to claim 1, wherein if the first change amount is greater than the first preset change amount threshold, recording the sleep state of the current time period as a motion state specifically includes :

If the first change amount is greater than the first preset change amount threshold, read a time interval corresponding to the current time period;

Recording the motion state corresponding to the time interval as the presence motion motion, and recording the motion intensity of the preset time interval as the first variation amount.
The sleep monitoring method according to any one of claims 1 to 5, wherein if the first change amount is greater than the first preset change amount threshold, the sleep state of the current time period is recorded as After the sport status includes:

Acquiring the sleep state in the next time period in sequence, and acquiring the first time period in which the sleep state is in the normal sleep state;

Calculating the exercise time in the motion state according to the current time period and the first time period.
The sleep monitoring method according to claim 6, wherein the calculating the exercise time in the motion state according to the current time period and the first time period comprises:

Determining a start time of the motion state according to all motion data included in the current time period, and determining an end time of the motion state according to all motion data included in the first preset time end;

The exercise time in which the exercise state continues is calculated based on the start time and the end time.
The sleep monitoring method according to claim 7, wherein said determining a start time of the motion state based on all motion data included in the current time period, and determining an end of the motion state based on all motion data included in the first time period The moments specifically include:

Comparing all the motion data included in the current time period and all the data included in the first time period with the preset motion data interval, wherein the change amount threshold is a change amount of the preset motion data interval;

Obtaining, in time sequence, first motion data that is not in the preset motion data interval of the current time period, and second motion data that is not in the preset data interval in the first time period to determine a motion state. Start time and end time.
The sleep monitoring method according to claim 1, wherein if the first change amount is greater than the first preset change amount threshold, the sleep state of the current time period is recorded as a motion state include:

Calculating a second change amount of the next time period, and comparing the first change amount and the second change amount with the second preset change amount threshold respectively;

When the first change amount is greater than or equal to the second preset change amount threshold, and the second change amount is less than the second preset change amount threshold, determining that the sleep state of the current time period is in the bed-away state, and recording according to the next time period Get out of bed.
The sleep monitoring method according to claim 9, wherein the method further comprises:

When the first change amount is less than the second preset change amount threshold, and the second change amount is greater than or equal to the second preset change amount threshold, determining that the sleep state of the current time period is in the bed state, and recording according to the next time period Bedtime.
The sleep monitoring method according to claim 9, wherein if the first change amount is greater than the change amount threshold, recording the sleep state of the preset time period as a motion state comprises:

Acquiring the sleep state in the next preset time period in sequence, and acquiring the first time period in which the sleep state is in the going to bed state;

The exercise time in the bed-away state is calculated according to the current time period and the first time period.
The sleep monitoring method according to claim 1, wherein the method further comprises:

If the first change amount is smaller than the first preset change amount threshold, compare the first change amount with the second preset change amount threshold;

When the first change amount is greater than the second preset change amount threshold, it is determined that the human body is in a normal sleep state.
The sleep monitoring method according to claim 12, wherein when the first change amount is greater than the second preset change amount threshold, determining that the human body is in a normal sleep state comprises:

Processing the BCG signal to divide it into a number of breathing cycles, wherein the breathing cycle comprises exhalation-inhalation-exhalation;

The exhalation points included in each breathing cycle are respectively offset by a preset offset along the time axis according to a preset rule;

Determining a time period corresponding to each breathing cycle according to the exhaled point after the offset;

The BCG signal is updated according to a time period corresponding to each breathing cycle, and the heart rate is extracted according to the updated BCG signal.
The sleep monitoring method according to claim 13, wherein the collecting the BCG signal and processing the BCG signal to divide it into a plurality of breathing cycles specifically comprises:

Collecting a BCG signal and performing low pass filtering on the BCG signal to obtain a respiratory signal;

All extreme points of the respiratory signal are acquired, and the respiratory signal is divided into several breathing cycles according to all the extreme points obtained.
The sleep monitoring method according to claim 14, wherein the obtaining all the extreme points of the respiratory signal and dividing the respiratory signal into a plurality of breathing periods according to all the extreme points obtained includes:

Obtaining a waveform curve corresponding to the waveform signal, and determining all maximum value points of the waveform signal according to the waveform curve;

The breathing signal is divided into a plurality of breathing cycles according to all the extracted maximum points, wherein the interval formed by the two adjacent maxima is one breathing cycle.
The sleep monitoring method according to claim 14, wherein the exposing the exhalation points of each breathing cycle to the preset offset along the time axis according to a preset rule comprises:

For each breathing cycle, the exhalation points included in the breathing cycle are sorted in chronological order;

According to the sorting order, the first exhalation point is shifted back by a preset offset along the time axis, and the second exhalation point is forwardly offset by a preset offset along the time axis.
The sleep monitoring method according to claim 16, wherein the sorting of the exhalation points included in the breathing cycle in chronological order for each respiratory cycle comprises:

Obtaining, according to the sorting order, a first moment corresponding to the first exhalation point and a second moment corresponding to the second exhalation point;

And calculating the preset offset according to the first time and the second time, wherein the preset offset=(second time−first time)/10.
The sleep monitoring method according to claim 13, wherein the updating the BCG signal according to a time period corresponding to each breathing cycle, and extracting the heart rate according to the updated BCG signal specifically includes:

Obtaining a first BCG signal corresponding to each time segment, and splicing each first BCG signal in time sequence to form an updated BCG signal;

The heart rate is extracted based on the updated BCG signal.
A computer readable storage medium, wherein the computer readable storage medium stores one or more programs, the one or more programs being executable by one or more processors to implement claim 1 The steps of the sleep monitoring method according to any one of the preceding claims.
A sleep monitoring device, comprising: a pressure sensor, a processor, a memory, and a communication bus; and the memory stores a computer readable program executable by the processor;

The communication bus implements connection communication between the processor and the memory;

The pressure sensor realizes acquisition of motion data, and transmits the collected motion data to a processor;

The processor of the present invention, when the computer readable program is executed, implements the steps of the sleep monitoring method of any of claims 1-18.